Project description
Solving the black box effect problem for machine learning
The recent growth and advancement of machine learning (ML) technologies have brought significant benefits and interactions with various sectors, impacting autonomous systems, decision-making, scientific discovery and medical diagnosis. However, as ML predictive systems become more sophisticated, their reasoning often becomes harder to interpret, raising concerns about safety. In this context, the ERC-funded SafetyBounds project will address this safety challenge, commonly referred to as the ‘black box effect’. Specifically, it will establish interpretable and accurate error bounds on ML predictions, from which valuable insights can be derived. Ultimately, the project will lay the groundwork for future practices in ML design and learning systems.
Objective
Recent breakthroughs in machine learning (ML) have brought about a transformative impact on decision-making, autonomous systems, medical diagnosis, and creation of new scientific knowledge. However, this progress has a major drawback: modern predictive systems are extremely complex and hard to interpret, a problem known as the black-box effect. The opaque nature of modern ML models, trained on increasingly diverse, incomplete, and noisy data, and later deployed in varying environments, hinders our ability to comprehend what drives inaccurate predictions, biased outcomes, and test time failures. Perhaps the most pressing question of our times is this: can we trust the predictions for future unseen instances obtained by black-box systems? The lack of practical guarantees on the limits of predictive performance poses a significant obstacle to deploying ML in applications that affect people's lives, opportunities, and science.
My overarching goal is to put precise, interpretable, and robust error bounds on ML predictions, communicating rigorously what can be honestly inferred from data. I call for the development of protective ecosystems that can be seamlessly plugged into any ML model to monitor and guarantee its safety.
This proposal introduces a unique interplay between statistics--the grammar of science--and ML--the art of learning from experience. Leveraging my expertise in both domains, I will show how statistical methodologies such as conformal prediction and test-martingales can empower ML, and how recent breakthroughs in ML such as semi-supervised learning and domain adaptation technologies can empower statistics. I will tackle challenges rooted in real-world problems concerning (1) availability and (2) quality of training data, as well as (3) test-time drifting data.
A successful outcome would not only lead to a timely and rigorous way toward safe ML, but may also significantly reform the way we develop, deploy, and interact with learning systems.
Keywords
Programme(s)
- HORIZON.1.1 - European Research Council (ERC) Main Programme
Topic(s)
Funding Scheme
HORIZON-ERC - HORIZON ERC GrantsHost institution
32000 Haifa
Israel